merge main into amd-staging

Change-Id: Ibdcc0f2aedf77ec18fff95baf8dc7ece0237635e

bolt/include/bolt/Core/BinaryData.h

@@ -226,7 +226,6 @@ inline raw_ostream &operator<<(raw_ostream &OS,
     Sep = ",\n        ";
     TotalCount += AccessInfo.Count;
   }
-  SS.flush();
 
   OS << TotalCount << " total counts : " << TempString;
   return OS;

bolt/include/bolt/Core/BinaryFunction.h

@@ -117,7 +117,6 @@ inline raw_ostream &operator<<(raw_ostream &OS,
     TotalCount += CSP.Count;
     TotalMispreds += CSP.Mispreds;
   }
-  SS.flush();
 
   OS << TotalCount << " (" << TotalMispreds << " misses) :" << TempString;
   return OS;

bolt/lib/Passes/RetpolineInsertion.cpp

@@ -181,7 +181,6 @@ std::string createRetpolineFunctionTag(BinaryContext &BC,
   if (BrInfo.isReg()) {
     BC.InstPrinter->printRegName(TagOS, BrInfo.BranchReg);
     TagOS << "_";
-    TagOS.flush();
     return Tag;
   }
 
@@ -212,7 +211,6 @@ std::string createRetpolineFunctionTag(BinaryContext &BC,
     BC.InstPrinter->printRegName(TagOS, MemRef.SegRegNum);
   }
 
-  TagOS.flush();
   return Tag;
 }
 

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -4245,7 +4245,6 @@ void RewriteInstance::addBoltInfoSection() {
          << "command line:";
   for (int I = 0; I < Argc; ++I)
     DescOS << " " << Argv[I];
-  DescOS.flush();
 
   // Encode as GNU GOLD VERSION so it is easily printable by 'readelf -n'
   const std::string BoltInfo =
@@ -4268,7 +4267,6 @@ void RewriteInstance::encodeBATSection() {
   raw_string_ostream DescOS(DescStr);
 
   BAT->write(*BC, DescOS);
-  DescOS.flush();
 
   const std::string BoltInfo =
       BinarySection::encodeELFNote("BOLT", DescStr, BinarySection::NT_BOLT_BAT);

bolt/lib/RuntimeLibs/InstrumentationRuntimeLibrary.cpp

@@ -314,7 +314,6 @@ std::string InstrumentationRuntimeLibrary::buildTables(BinaryContext &BC) {
   }
   // Our string table lives immediately after descriptions vector
   OS << Summary->StringTable;
-  OS.flush();
 
   return TablesStr;
 }

bolt/test/X86/log.test

@@ -6,7 +6,7 @@ RUN: yaml2obj %p/Inputs/blarge.yaml &> %t.exe
 RUN: llvm-bolt %t.exe -o %t.null --data %p/Inputs/blarge.fdata -v=2 \
 RUN:   --reorder-blocks=normal --print-finalized --log-file=%t.log  2>&1 \
 RUN:   | FileCheck --check-prefix=CHECK --allow-empty %s
-RUN: cat %t.log | FileCheck %s --check-prefix=CHECK-LOG
+RUN: FileCheck %s --check-prefix=CHECK-LOG --input-file %t.log
 
 CHECK-NOT: BOLT-INFO
 CHECK-NOT: BOLT-WARNING
@@ -16,4 +16,4 @@ CHECK-NOT: BOLT-ERROR
 CHECK-LOG: BOLT-INFO: Target architecture
 CHECK-LOG: BOLT-INFO: BOLT version
 CHECK-LOG: BOLT-INFO: basic block reordering modified layout
-CHECK-LOG:    Binary Function "usqrt"
+CHECK-LOG:    Binary Function "main"

bolt/test/perf2bolt/perf_test.test

@@ -3,15 +3,12 @@
 REQUIRES: system-linux, perf
 
 RUN: %clang %S/Inputs/perf_test.c -fuse-ld=lld -Wl,--script=%S/Inputs/perf_test.lds -o %t
-RUN: perf record -e cycles:u -o %t2 -- %t
+RUN: perf record -Fmax -e cycles:u -o %t2 -- %t
 RUN: perf2bolt %t -p=%t2 -o %t3 -nl -ignore-build-id 2>&1 | FileCheck %s
 
 CHECK-NOT: PERF2BOLT-ERROR
 CHECK-NOT: !! WARNING !! This high mismatch ratio indicates the input binary is probably not the same binary used during profiling collection.
 
 RUN: %clang %S/Inputs/perf_test.c -no-pie -fuse-ld=lld -o %t4
-RUN: perf record -e cycles:u -o %t5 -- %t4
-RUN: perf2bolt %t4 -p=%t5 -o %t6 -nl -ignore-build-id 2>&1 | FileCheck %s --check-prefix=CHECK-NO-PIE
-
-CHECK-NO-PIE-NOT: PERF2BOLT-ERROR
-CHECK-NO-PIE-NOT: !! WARNING !! This high mismatch ratio indicates the input binary is probably not the same binary used during profiling collection.
+RUN: perf record -Fmax -e cycles:u -o %t5 -- %t4
+RUN: perf2bolt %t4 -p=%t5 -o %t6 -nl -ignore-build-id 2>&1 | FileCheck %s

clang/docs/OpenMPSupport.rst

@@ -294,7 +294,7 @@ implementation.
 +------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
 | misc                         | error directive                                              | :good:`done`             | D139166                                                               |
 +------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
-| misc                         | scope construct                                              | :none:`worked on`        | D157933                                                               |
+| misc                         | scope construct                                              | :good:`done`             | D157933, https://github.com/llvm/llvm-project/pull/109197             |
 +------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+
 | misc                         | routines for controlling and querying team regions           | :part:`partial`          | D95003 (libomp only)                                                  |
 +------------------------------+--------------------------------------------------------------+--------------------------+-----------------------------------------------------------------------+

clang/include/clang/Frontend/ASTUnit.h

@@ -692,8 +692,8 @@ class ASTUnit {
   ///
   /// \returns - The initialized ASTUnit or null if the AST failed to load.
   static std::unique_ptr<ASTUnit>
-  LoadFromASTFile(const std::string &Filename,
-                  const PCHContainerReader &PCHContainerRdr, WhatToLoad ToLoad,
+  LoadFromASTFile(StringRef Filename, const PCHContainerReader &PCHContainerRdr,
+                  WhatToLoad ToLoad,
                   IntrusiveRefCntPtr<DiagnosticsEngine> Diags,
                   const FileSystemOptions &FileSystemOpts,
                   std::shared_ptr<HeaderSearchOptions> HSOpts,

clang/lib/AST/ByteCode/Compiler.cpp

@@ -431,6 +431,7 @@ bool Compiler<Emitter>::VisitCastExpr(const CastExpr *CE) {
   case CK_NoOp:
   case CK_UserDefinedConversion:
   case CK_AddressSpaceConversion:
+  case CK_CPointerToObjCPointerCast:
     return this->delegate(SubExpr);
 
   case CK_BitCast: {
@@ -3116,21 +3117,22 @@ bool Compiler<Emitter>::VisitCXXNewExpr(const CXXNewExpr *E) {
         if (!this->discard(Arg1))
           return false;
         IsNoThrow = true;
-      } else if (Ctx.getLangOpts().CPlusPlus26 &&
-                 OperatorNew->isReservedGlobalPlacementOperator()) {
+      } else {
+        // Invalid unless we have C++26 or are in a std:: function.
+        if (!this->emitInvalidNewDeleteExpr(E, E))
+          return false;
+
         // If we have a placement-new destination, we'll later use that instead
         // of allocating.
-        PlacementDest = Arg1;
-      } else {
-        return this->emitInvalidNewDeleteExpr(E, E);
+        if (OperatorNew->isReservedGlobalPlacementOperator())
+          PlacementDest = Arg1;
       }
-
     } else {
+      // Always invalid.
       return this->emitInvalid(E);
     }
-  } else if (!OperatorNew->isReplaceableGlobalAllocationFunction()) {
+  } else if (!OperatorNew->isReplaceableGlobalAllocationFunction())
     return this->emitInvalidNewDeleteExpr(E, E);
-  }
 
   const Descriptor *Desc;
   if (!PlacementDest) {

clang/lib/AST/ByteCode/Interp.cpp

@@ -1293,6 +1293,13 @@ bool CheckNewTypeMismatch(InterpState &S, CodePtr OpPC, const Expr *E,
   if (!CheckStore(S, OpPC, Ptr))
     return false;
 
+  if (!InvalidNewDeleteExpr(S, OpPC, E))
+    return false;
+
+  // Assume proper types in std functions.
+  if (S.Current->isStdFunction())
+    return true;
+
   const auto *NewExpr = cast<CXXNewExpr>(E);
   QualType StorageType = Ptr.getType();
 
@@ -1334,10 +1341,16 @@ bool InvalidNewDeleteExpr(InterpState &S, CodePtr OpPC, const Expr *E) {
   assert(E);
   const auto &Loc = S.Current->getSource(OpPC);
 
+  if (S.getLangOpts().CPlusPlus26)
+    return true;
+
   if (const auto *NewExpr = dyn_cast<CXXNewExpr>(E)) {
     const FunctionDecl *OperatorNew = NewExpr->getOperatorNew();
 
     if (!S.getLangOpts().CPlusPlus26 && NewExpr->getNumPlacementArgs() > 0) {
+      // This is allowed pre-C++26, but only an std function.
+      if (S.Current->isStdFunction())
+        return true;
       S.FFDiag(Loc, diag::note_constexpr_new_placement)
           << /*C++26 feature*/ 1 << E->getSourceRange();
     } else if (NewExpr->getNumPlacementArgs() == 1 &&

clang/lib/AST/ByteCode/InterpBuiltin.cpp

@@ -1345,8 +1345,7 @@ static bool interp__builtin_operator_new(InterpState &S, CodePtr OpPC,
   assert(!ElemT);
   // Structs etc.
   const Descriptor *Desc = S.P.createDescriptor(
-      Call, ElemType.getTypePtr(),
-      NumElems.ule(1) ? std::nullopt : Descriptor::InlineDescMD,
+      Call, ElemType.getTypePtr(), Descriptor::InlineDescMD,
       /*IsConst=*/false, /*IsTemporary=*/false, /*IsMutable=*/false,
       /*Init=*/nullptr);
 

clang/lib/AST/ByteCode/InterpFrame.cpp

@@ -257,3 +257,13 @@ SourceRange InterpFrame::getRange(CodePtr PC) const {
 
   return S.getRange(Func, PC);
 }
+
+bool InterpFrame::isStdFunction() const {
+  if (!Func)
+    return false;
+  for (const DeclContext *DC = Func->getDecl(); DC; DC = DC->getParent())
+    if (DC->isStdNamespace())
+      return true;
+
+  return false;
+}

clang/lib/AST/ByteCode/InterpFrame.h

@@ -117,6 +117,8 @@ class InterpFrame final : public Frame {
 
   unsigned getDepth() const { return Depth; }
 
+  bool isStdFunction() const;
+
   void dump() const { dump(llvm::errs(), 0); }
   void dump(llvm::raw_ostream &OS, unsigned Indent = 0) const;
 

clang/lib/Basic/Targets/BPF.cpp

@@ -37,6 +37,7 @@ void BPFTargetInfo::getTargetDefines(const LangOptions &Opts,
   }
 
   Builder.defineMacro("__BPF_FEATURE_ADDR_SPACE_CAST");
+  Builder.defineMacro("__BPF_FEATURE_MAY_GOTO");
 
   if (CPU.empty())
     CPU = "v3";
@@ -48,7 +49,6 @@ void BPFTargetInfo::getTargetDefines(const LangOptions &Opts,
 
   std::string CpuVerNumStr = CPU.substr(1);
   Builder.defineMacro("__BPF_CPU_VERSION__", CpuVerNumStr);
-  Builder.defineMacro("__BPF_FEATURE_MAY_GOTO");
 
   int CpuVerNum = std::stoi(CpuVerNumStr);
   if (CpuVerNum >= 2)

clang/lib/CodeGen/CGBuiltin.cpp

@@ -587,9 +587,10 @@ static Value *emitCallMaybeConstrainedFPBuiltin(CodeGenFunction &CGF,
 // matching the argument type. It is assumed that only the first argument is
 // overloaded.
 template <unsigned N>
-Value *emitBuiltinWithOneOverloadedType(CodeGenFunction &CGF, const CallExpr *E,
-                                        unsigned IntrinsicID,
-                                        llvm::StringRef Name = "") {
+static Value *emitBuiltinWithOneOverloadedType(CodeGenFunction &CGF,
+                                               const CallExpr *E,
+                                               unsigned IntrinsicID,
+                                               llvm::StringRef Name = "") {
   static_assert(N, "expect non-empty argument");
   SmallVector<Value *, N> Args;
   for (unsigned I = 0; I < N; ++I)
@@ -18573,7 +18574,7 @@ llvm::Value *CodeGenFunction::EmitScalarOrConstFoldImmArg(unsigned ICEArguments,
 }
 
 // Return dot product intrinsic that corresponds to the QT scalar type
-Intrinsic::ID getDotProductIntrinsic(CGHLSLRuntime &RT, QualType QT) {
+static Intrinsic::ID getDotProductIntrinsic(CGHLSLRuntime &RT, QualType QT) {
   if (QT->isFloatingType())
     return RT.getFDotIntrinsic();
   if (QT->isSignedIntegerType())

clang/lib/CodeGen/CGOpenMPRuntime.cpp

@@ -1514,7 +1514,7 @@ llvm::Type *CGOpenMPRuntime::getKmpc_MicroPointerTy() {
   return llvm::PointerType::getUnqual(Kmpc_MicroTy);
 }
 
-llvm::OffloadEntriesInfoManager::OMPTargetDeviceClauseKind
+static llvm::OffloadEntriesInfoManager::OMPTargetDeviceClauseKind
 convertDeviceClause(const VarDecl *VD) {
   std::optional<OMPDeclareTargetDeclAttr::DevTypeTy> DevTy =
       OMPDeclareTargetDeclAttr::getDeviceType(VD);
@@ -1537,7 +1537,7 @@ convertDeviceClause(const VarDecl *VD) {
   }
 }
 
-llvm::OffloadEntriesInfoManager::OMPTargetGlobalVarEntryKind
+static llvm::OffloadEntriesInfoManager::OMPTargetGlobalVarEntryKind
 convertCaptureClause(const VarDecl *VD) {
   std::optional<OMPDeclareTargetDeclAttr::MapTypeTy> MapType =
       OMPDeclareTargetDeclAttr::isDeclareTargetDeclaration(VD);
@@ -8885,7 +8885,7 @@ static ValueDecl *getDeclFromThisExpr(const Expr *E) {
 
 /// Emit a string constant containing the names of the values mapped to the
 /// offloading runtime library.
-llvm::Constant *
+static llvm::Constant *
 emitMappingInformation(CodeGenFunction &CGF, llvm::OpenMPIRBuilder &OMPBuilder,
                        MappableExprsHandler::MappingExprInfo &MapExprs) {
 
@@ -9527,8 +9527,8 @@ static llvm::Value *emitDeviceID(
   return DeviceID;
 }
 
-llvm::Value *emitDynCGGroupMem(const OMPExecutableDirective &D,
-                               CodeGenFunction &CGF) {
+static llvm::Value *emitDynCGGroupMem(const OMPExecutableDirective &D,
+                                      CodeGenFunction &CGF) {
   llvm::Value *DynCGroupMem = CGF.Builder.getInt32(0);
 
   if (auto *DynMemClause = D.getSingleClause<OMPXDynCGroupMemClause>()) {

clang/lib/CodeGen/CGStmtOpenMP.cpp

@@ -3109,8 +3109,8 @@ GetAlignedMapping(const OMPLoopDirective &S, CodeGenFunction &CGF) {
 
 // Pass OMPLoopDirective (instead of OMPSimdDirective) to make this function
 // available for "loop bind(thread)", which maps to "simd".
-void emitOMPSimdDirective(const OMPLoopDirective &S, CodeGenFunction &CGF,
-                          CodeGenModule &CGM) {
+static void emitOMPSimdDirective(const OMPLoopDirective &S,
+                                 CodeGenFunction &CGF, CodeGenModule &CGM) {
   bool UseOMPIRBuilder =
       CGM.getLangOpts().OpenMPIRBuilder && isSimdSupportedByOpenMPIRBuilder(S);
   if (UseOMPIRBuilder) {
@@ -4368,8 +4368,8 @@ convertClauseKindToSchedKind(OpenMPScheduleClauseKind ScheduleClauseKind) {
 
 // Pass OMPLoopDirective (instead of OMPForDirective) to make this function
 // available for "loop bind(parallel)", which maps to "for".
-void emitOMPForDirective(const OMPLoopDirective &S, CodeGenFunction &CGF,
-                         CodeGenModule &CGM, bool HasCancel) {
+static void emitOMPForDirective(const OMPLoopDirective &S, CodeGenFunction &CGF,
+                                CodeGenModule &CGM, bool HasCancel) {
   bool HasLastprivates = false;
   bool UseOMPIRBuilder = CGM.getLangOpts().OpenMPIRBuilder &&
                          isForSupportedByOpenMPIRBuilder(S, HasCancel);
@@ -5828,7 +5828,7 @@ void CodeGenFunction::EmitOMPTaskwaitDirective(const OMPTaskwaitDirective &S) {
   CGM.getOpenMPRuntime().emitTaskwaitCall(*this, S.getBeginLoc(), Data);
 }
 
-bool isSupportedByOpenMPIRBuilder(const OMPTaskgroupDirective &T) {
+static bool isSupportedByOpenMPIRBuilder(const OMPTaskgroupDirective &T) {
   return T.clauses().empty();
 }
 
@@ -6458,8 +6458,9 @@ void CodeGenFunction::EmitOMPDistributeLoop(const OMPLoopDirective &S,
 
 // Pass OMPLoopDirective (instead of OMPDistributeDirective) to make this
 // function available for "loop bind(teams)", which maps to "distribute".
-void emitOMPDistributeDirective(const OMPLoopDirective &S, CodeGenFunction &CGF,
-                                CodeGenModule &CGM) {
+static void emitOMPDistributeDirective(const OMPLoopDirective &S,
+                                       CodeGenFunction &CGF,
+                                       CodeGenModule &CGM) {
   auto &&CodeGen = [&S](CodeGenFunction &CGF, PrePostActionTy &) {
     CGF.EmitOMPDistributeLoop(S, emitOMPLoopBodyWithStopPoint, S.getInc());
   };

clang/lib/CodeGen/CodeGenModule.cpp

@@ -788,8 +788,9 @@ getLLVMVisibility(clang::LangOptions::VisibilityFromDLLStorageClassKinds K) {
   llvm_unreachable("unknown option value!");
 }
 
-void setLLVMVisibility(llvm::GlobalValue &GV,
-                       std::optional<llvm::GlobalValue::VisibilityTypes> V) {
+static void
+setLLVMVisibility(llvm::GlobalValue &GV,
+                  std::optional<llvm::GlobalValue::VisibilityTypes> V) {
   if (!V)
     return;
 
@@ -4235,8 +4236,8 @@ TargetMVPriority(const TargetInfo &TI,
 // in the cases of CPUDispatch, this causes issues. This also makes sure we
 // work with internal linkage functions, so that the same function name can be
 // used with internal linkage in multiple TUs.
-llvm::GlobalValue::LinkageTypes getMultiversionLinkage(CodeGenModule &CGM,
-                                                       GlobalDecl GD) {
+static llvm::GlobalValue::LinkageTypes
+getMultiversionLinkage(CodeGenModule &CGM, GlobalDecl GD) {
   const FunctionDecl *FD = cast<FunctionDecl>(GD.getDecl());
   if (FD->getFormalLinkage() == Linkage::Internal)
     return llvm::GlobalValue::InternalLinkage;

clang/lib/CodeGen/SanitizerMetadata.cpp

@@ -27,7 +27,7 @@ static bool isAsanHwasanOrMemTag(const SanitizerSet &SS) {
                      SanitizerKind::HWAddress | SanitizerKind::MemTag);
 }
 
-SanitizerMask expandKernelSanitizerMasks(SanitizerMask Mask) {
+static SanitizerMask expandKernelSanitizerMasks(SanitizerMask Mask) {
   if (Mask & (SanitizerKind::Address | SanitizerKind::KernelAddress))
     Mask |= SanitizerKind::Address | SanitizerKind::KernelAddress;
   // Note: KHWASan doesn't support globals.

clang/lib/CrossTU/CrossTranslationUnit.cpp

@@ -566,9 +566,9 @@ CrossTranslationUnitContext::ASTLoader::loadFromDump(StringRef ASTDumpPath) {
   IntrusiveRefCntPtr<DiagnosticsEngine> Diags(
       new DiagnosticsEngine(DiagID, &*DiagOpts, DiagClient));
   return ASTUnit::LoadFromASTFile(
-      std::string(ASTDumpPath.str()),
-      CI.getPCHContainerOperations()->getRawReader(), ASTUnit::LoadEverything,
-      Diags, CI.getFileSystemOpts(), CI.getHeaderSearchOptsPtr());
+      ASTDumpPath, CI.getPCHContainerOperations()->getRawReader(),
+      ASTUnit::LoadEverything, Diags, CI.getFileSystemOpts(),
+      CI.getHeaderSearchOptsPtr());
 }
 
 /// Load the AST from a source-file, which is supposed to be located inside the

clang/lib/Frontend/ASTUnit.cpp

@@ -802,7 +802,7 @@ void ASTUnit::ConfigureDiags(IntrusiveRefCntPtr<DiagnosticsEngine> Diags,
 }
 
 std::unique_ptr<ASTUnit> ASTUnit::LoadFromASTFile(
-    const std::string &Filename, const PCHContainerReader &PCHContainerRdr,
+    StringRef Filename, const PCHContainerReader &PCHContainerRdr,
     WhatToLoad ToLoad, IntrusiveRefCntPtr<DiagnosticsEngine> Diags,
     const FileSystemOptions &FileSystemOpts,
     std::shared_ptr<HeaderSearchOptions> HSOpts,